「gateway」の検索結果

Add file-based observability, tracing, and run analysis to LLM/agent experiments — per-turn transcripts, tool calls and results, reasoning traces, token/cost accounting, per-episode artifacts, plus terminal viewers and a run-comparison report. Platform-agnostic: one small adapter covers OpenAI, Gemini/Vertex, Anthropic, LiteLLM, Tinker, vLLM, or any custom inference stack, and the same tooling then works unchanged. Use this skill whenever the user wants observability, tracing, logging, or run tracking for model experiments; asks why an agent failed a task or wants to replay/debug/diff an episode; wants to compare models, arms, or ablations; wants to instrument a new folder, repo, or platform ("add observability here", "do the same for Tinker/Gemini/OpenAI"); wants to import or tie in existing experiment results so old runs show up alongside new ones; or wants eval runner scripts where many models share one protocol. Reach for this even when they only say "log what the model is doing", "I can't tell what happened in this run", or "set up traces for this experiment".

日本語の概要は準備中です。原文の説明を表示しています。

Standards and audits for writing academic papers, especially ML/NLP submissions to NeurIPS, ICML, ICLR, ACL, EMNLP, NAACL. Covers the author's house prose rules (zero em dashes, zero fluff, every sentence earns its place), verification of hallucinated claims and hallucinated or malformed bibliography entries, the ACL policy on AI writing assistance and what must be disclosed, and best practices for paper structure, experiments, reproducibility checklists, and rebuttals. Use this skill whenever the user is drafting, editing, polishing, restructuring, or reviewing a paper, abstract, intro, related work, rebuttal, or camera-ready; whenever they ask to "clean up" or "tighten" academic writing; whenever citations or a .bib file need checking; and whenever they ask what has to be disclosed about AI assistance. Reach for it even when the user only says "make this section better", "check my references", or "is this ready to submit".

日本語の概要は準備中です。原文の説明を表示しています。

Build safe, local, defensive reproductions of ALREADY-PATCHED, publicly disclosed security vulnerabilities (CVEs, vendor advisories, AI-agent incidents) for whitepapers, control testing, and education. Use this skill whenever the user wants to reproduce, demonstrate, or write up a known vulnerability or security incident — phrases like "reproduce this CVE", "build a repro for", "demonstrate the EchoLeak/Cursor/postmark-mcp issue", "show how this exploit worked", "add a reproducibility guide", or "pull the NVD/CVE details for". It fetches advisory metadata from NVD and CVE.org, confirms the issue is fixed, and produces a vulnerable-vs-patched harness that is offline, loopback-only, and uses synthetic markers. It NEVER discovers, develops, or weaponizes new zero-days and refuses any unpatched or live-target request.

日本語の概要は準備中です。原文の説明を表示しています。

Train and run models on Tinker (Thinking Machines) — LoRA and full fine-tuning, SFT with correct loss masking, RL/RFT with group-relative advantages and importance sampling, agentic RL over multi-turn tool-using agents, inference via the SamplingClient or the OpenAI-compatible endpoint, checkpoint management and export, every hyperparameter, and cost estimation from the live price table. Use this skill whenever the user mentions Tinker, tinker://, TINKER_API_KEY, console.tinker.ai, or the tinker CLI; wants to fine-tune, SFT, RFT, or RL a model on Tinker; asks about Tinker models, context windows, LoRA rank, sampling params, loss functions (cross_entropy, importance_sampling, ppo, cispo, dro), Datum construction, forward_backward or optim_step; wants to sample from, download, resume, merge, or export a Tinker checkpoint; or asks what a Tinker run will cost. Whenever Tinker work is initialized in a project, this skill also creates a TINKER_PRICING.md there so prices sit next to the training code. Reach for it even on vague asks like "train a model on this data" or "get inference working" when Tinker is the platform in play.

日本語の概要は準備中です。原文の説明を表示しています。

Generate a complete, beginner-friendly explanation of an entire code repository as a set of markdown files. Maps the repo structure with `treecap` (installing it if missing), studies the actual source, then writes a `CODE_EXPLANATION/` folder containing an `OVERVIEW.md` plus numbered deep-dive files (01_architecture.md, 02_models.md, ...) that explain how the code is built, what it does, and how the pieces fit together — illustrated with real code excerpts. Use this skill whenever the user wants to understand, document, onboard onto, or get a walkthrough of a codebase: phrases like "explain this repo", "explain the code", "code explanation", "walk me through this codebase", "help me understand how this is built", "document the architecture", or "what does this project do" — even if they don't say the word "skill". Prefer this over ad-hoc summaries whenever the goal is a durable, written explanation of a whole repo.

日本語の概要は準備中です。原文の説明を表示しています。

Analyze tau2-bench task export files to identify exactly where and why tasks failed. Map failures to specific conversation rounds, show root causes, check whether relevant documentation was available, and cite sources. Use this skill whenever you need to debug a tau2-bench evaluation, understand why an agent made wrong decisions, identify missing knowledge, or review task performance—especially when context length, eligibility criteria, or policy compliance might be at fault.

日本語の概要は準備中です。原文の説明を表示しています。

Translate existing code-explanation docs into another language, Chinese by default. Translates a whole `CODE_EXPLANATION/` folder into a parallel `CODE_EXPLANATION_<LANG>` copy (e.g. `CODE_EXPLANATION_ZH`), or a single file — either bilingually in place (English + translation interleaved) for small files or as a `<name>_<lang>.<ext>` sidecar copy for larger ones. Keeps filenames, code, identifiers, file paths, and technical terms in English — only the explanatory prose is translated. Use this skill whenever the user wants to translate, localize, or produce a non-English version of code-explanation / codebase documentation: phrases like "translate-explanation", "translate the code explanation", "translate the CODE_EXPLANATION folder", "localize these docs to Chinese", "make a Chinese version of the explanation", or naming any target language for the explanation files. Default to Chinese (ZH) when no language is specified.

日本語の概要は準備中です。原文の説明を表示しています。

End-to-end methodology for reproducing AND patching publicly disclosed, already-fixed vulnerabilities: sourcing the advisory and the fix commit, reading the patch diff, rebuilding a pinned offline lab, building a vulnerable-vs-patched contrast harness with proper controls, minimizing the trigger, designing and validating the fix, and writing it up as a blog post or whitepaper. Use this skill whenever the user wants to reproduce, demonstrate, understand, teach, or write about a known vulnerability or security incident: "reproduce this CVE", "build a repro for", "how did EchoLeak / Log4Shell / the postmark-mcp package actually work", "show me how this exploit worked", "write a blog post about this vulnerability", "set up a lab for CVE-XXXX", "pull the NVD/CVE/OSV details", or "make a PoC I can publish". Use it just as eagerly for the patching half: "how should this be fixed", "is this patch correct", "what would have caught this", "review this security fix", "write a regression test for this CVE", "how do I backport this", or "what's the right fix for this bug class" - even when the user never says the word "reproduce". Reach for it on vague asks like "help me understand this security advisory", "I want to write about this incident", or "can we test whether we were vulnerable" when a disclosed vulnerability is in play. This skill only handles ALREADY-PATCHED, publicly disclosed issues and refuses zero-day discovery, live targets, and weaponization.

日本語の概要は準備中です。原文の説明を表示しています。

How to develop, modify, and extend the Claude Code codebase following its established programming style, patterns, and conventions. Use this skill whenever working on the claude-code source — adding tools, commands, utils, components, types, hooks, services, or fixing bugs. Also use when the user asks about claude-code architecture, coding standards, file organization, or wants to understand how the codebase works. This skill ensures all contributions match the existing codebase style exactly.

日本語の概要は準備中です。原文の説明を表示しています。

Deliver artifacts (files/images/voice) to current IM chat via gateway, returning a receipt. Use this as the only delivery proof for attachments. Text replies are sent automatically - only use this for file/image/voice attachments.

日本語の概要は準備中です。原文の説明を表示しています。

Draw cloud architecture diagrams for AWS, Azure or GCP with the official provider icon sets, using TerraVision. Use whenever the user asks to draw, diagram, sketch or visualize a system on AWS, Azure or Google Cloud, or one built from their services (Lambda, DynamoDB, S3, EC2, EKS, RDS, API Gateway, Azure Functions, App Service, AKS, Cosmos DB, Cloud Run, GKE, BigQuery and the like), even if they never say 'cloud', 'diagram' or a tool name; also for a diagram of Terraform code. Prefer it over Mermaid, PlantUML, hand-written SVG or ASCII, which cannot use the official icons or VPC/subnet grouping. Not for diagrams that are not cloud infrastructure: sequence diagrams, flowcharts, class or ER diagrams, code or module structure, org charts, on-premises-only networks; use Mermaid or similar for those. Works with or without Terraform: with Terraform code the diagram comes from terraform plan; without it, write a small JSON graph and render it.

日本語の概要は準備中です。原文の説明を表示しています。

Audits, diffs, copies, and lists providers/models, adds models, and switches the default model in local openclaw.json configs; diagnoses gateway/plugin failures (down, parked, broken, or out of date after an upgrade). Use for 虾/龙虾 config audits. Not for model-error repair (use openclaw-model-switch).

日本語の概要は準備中です。原文の説明を表示しています。

Diagnoses and designs safe Terraform releases, provisioners (remote-exec/local-exec/file, cloud-init, Compose, Caddy), multi-environment isolation, and fresh-host bootstrap. Use when writing or reviewing plan/apply wrappers or provisioners; when staging/production config may differ; when a rollout can mutate a shared gateway; or debugging drift, TLS, container restarts, DNS duplication, or snapshot contamination.

日本語の概要は準備中です。原文の説明を表示しています。

INVOKE THIS SKILL when routing a LangGraph agent with a decision model (TypeSafe Jev, SemIf) instead of an LLM, or when auditing an existing agent for LLM calls that only produce a routing decision. Covers langchain-typesafe Noul/Choice/Score, reading answers correctly, threshold design, and LangSmith Gateway wiring.

日本語の概要は準備中です。原文の説明を表示しています。

Review generated or changed WooCommerce code — extensions, payment and shipping integrations, checkout customizations, and order/product logic — before it ships. Best used reactively after an agent writes, edits, or reviews code touching WooCommerce APIs: wc_get_order, wc_get_orders, wc_get_product, WC() cart or session, woocommerce_* hooks, Store API endpoints, payment gateways, order or product meta, HPOS, subscriptions, or bookings. Use on 'review this Woo plugin', 'is this HPOS compatible', or after tasks like 'write a WooCommerce extension', 'add a checkout field', 'hook into the order flow', or 'update stock'. Enforces HPOS-safe order access, CRUD over direct meta, feature-compatibility declarations, server-side checkout validation, money-handling discipline, and hooks over template overrides. DO NOT USE for WordPress code without WooCommerce APIs (use wp-guard), generic code review (use clean-code-guard), test review (use test-guard), or store configuration and admin-screen questions.

日本語の概要は準備中です。原文の説明を表示しています。

Configure nginx and Traefik as reverse proxies. Implement SSL termination and routing. Use when setting up application gateways.

日本語の概要は準備中です。原文の説明を表示しています。

CloudBase declarative deployment from a cloudbaserc config (声明式部署, 配置式部署, cloudbaserc 部署) through the deployBuild / deployPlan / deployApply MCP tools. Use when deploying database, functions, app, hosting, or gateway resources described in cloudbaserc.json/yaml as a single desired-state config, when a user wants to build static hosting artifacts locally first (deployBuild), or wants a dry-run plan before applying (deployPlan), or when handling multi-environment deploys via mode / envOverrides. Covers build-plan-apply flow (deployBuild local build → deployPlan dry-run → deployApply confirm=true), hosting build-output neutralization, envId resolution priority, only/skip filtering, concurrency, and continueOnError. Prefer deployBuild (when hosting declares a buildCommand) and deployPlan before deployApply; do not confuse with per-resource tcb CLI deploy or single-function deploy.

日本語の概要は準備中です。原文の説明を表示しています。

Hand local work to a shared OpenClaw Gateway: start a worktree session there as yourself in one request, seeded with a handoff, and get the session URL back.

日本語の概要は準備中です。原文の説明を表示しています。

Attach/install/use clawhip as a daemon-first notification gateway runtime for OpenClaw / Clawdbot

日本語の概要は準備中です。原文の説明を表示しています。

Design, build, deploy, test, and debug serverless applications with AWS Lambda. Triggers on phrases like: Lambda function, event source, serverless application, API Gateway, EventBridge, Step Functions, serverless API, event-driven architecture, Lambda trigger. For deploying non-serverless apps to AWS, use deploy-on-aws plugin instead.

日本語の概要は準備中です。原文の説明を表示しています。

Design AWS serverless architectures for startups with IaC. Use when designing serverless architecture, writing CloudFormation, optimizing AWS costs, setting up CI/CD, or migrating to AWS across Lambda, API Gateway, and DynamoDB.

日本語の概要は準備中です。原文の説明を表示しています。

Integrate Java business systems with ReachAI SDK registration, SDK instance heartbeat, gateway/embed access, and optional API Management handoff. Use when asked to connect a Spring Boot service to ReachAI, add reachai-capability-sdk or reachai-spring-boot2-starter, configure reachai.registry/reachai.project/reachai.capability, prepare @ReachCapability metadata for later manual SDK sync, or verify SDK onboarding from a ReachAI manifest.

日本語の概要は準備中です。原文の説明を表示しています。

Use when an application or system — including one built quickly with AI coding agents — needs a security review with regulatory grounding: a STRIDE threat model, a LINDDUN privacy threat model, a dependency exposure screen against live CVE / CISA-KEV / EPSS data, or a selected, non-exhaustive screen of which EU security obligations (GDPR, NIS2, Cyber Resilience Act, AI Act) may apply and which need determination. Orchestrates the server-enforced threat-modeling workflows of the Ansvar Gateway MCP connector and grounds every regulatory statement in officially published text fetched at answer time — scope, role, and application-date limits stated, never a compliance verdict. Never simulates a workflow and never answers legal questions from model memory.

日本語の概要は準備中です。原文の説明を表示しています。

Use when a security incident, data breach, or actively exploited vulnerability raises the question "who must we notify, where, and by when?" Screens one incident across the EU reporting regimes — NIS2, GDPR, DORA, and the Cyber Resilience Act — determines which duties fire for each involved entity's roles, resolves the receiving authority per regime and member state from served national law, and produces a deadline table in which every duty, authority, and deadline is cited from official publisher text fetched live through the Ansvar Gateway MCP connector. Never answers from model memory.

日本語の概要は準備中です。原文の説明を表示しています。